Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification
This addresses privacy concerns for data holders in graph-based tasks by enabling collaborative training without sharing sensitive information, though it is incremental as it adapts existing GNN models to a federated setting.
The paper tackles the data isolation problem in graph neural networks by proposing VFGNN, a vertically federated learning paradigm for privacy-preserving node classification, which splits computations between data holders and a server and applies differential privacy, with experiments on three benchmarks showing its effectiveness.
Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes. High-performance GNN models always depend on both rich features and complete edge information in graph. However, such information could possibly be isolated by different data holders in practice, which is the so-called data isolation problem. To solve this problem, in this paper, we propose VFGNN, a federated GNN learning paradigm for privacy-preserving node classification task under data vertically partitioned setting, which can be generalized to existing GNN models. Specifically, we split the computation graph into two parts. We leave the private data (i.e., features, edges, and labels) related computations on data holders, and delegate the rest of computations to a semi-honest server. We also propose to apply differential privacy to prevent potential information leakage from the server. We conduct experiments on three benchmarks and the results demonstrate the effectiveness of VFGNN.